AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

TIPI: Test Time Adaptation With Transformation Invariance

A. Tuan Nguyen, Thanh Nguyen-Tang, Ser-Nam Lim, Philip H.S. Torr

CVPR 2023 · Label-efficient and robust learning › Test-time adaptation · approach: Realistic and stable test-time adaptation · 27 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use transformation-invariance adaptation instead of entropy minimizationTest-time adaptation on CIFAR10-C · CIFAR10-C (average)accuracy: 65.5 -> 80.4Improved
Use transformation-invariance adaptation instead of entropy minimizationTest-time adaptation on CIFAR100-C · CIFAR100-C (average)accuracy: 39.8 -> 63.2Improved
Use transformation-invariance adaptation instead of test-time batch statisticsTest-time adaptation on ImageNet-C · ImageNet-C (average)accuracy: 47.2 -> 55.0Improved
Use transformation-invariance adaptation instead of entropy minimizationTest-time adaptation on CIFAR10-C · CIFAR10-C (batch size 2)accuracy: 17.4 -> 78.6Improved
Use transformation-invariance adaptation instead of entropy minimizationTest-time adaptation on CIFAR100-C · CIFAR100-C (batch size 2)accuracy: 1.5 -> 56.3Improved
Use transformation-invariance adaptation instead of entropy minimizationTest-time adaptation on ImageNet-C · ImageNet-C (batch size 2)accuracy: 0.8 -> 45.2Improved
Use transformation-invariance adaptation instead of entropy minimizationSVHN-to-MNIST adaptation · SVHN→MNIST (batch size 128)accuracy: 90.7 -> 91.6Improved
Use transformation-invariance adaptation instead of T3ASVHN-to-MNIST-M adaptation · SVHN→MNIST-M (batch size 4)accuracy: 60.7 -> 64.2Improved
Use transformation-invariance adaptation instead of entropy minimizationSVHN-to-USPS adaptation · SVHN→USPS (batch size 128)accuracy: 90.4 -> 93.9Improved
Use transformation-invariance adaptation instead of test-time batch statisticsTest-time adaptation on VisDA17 · VisDA17 (average)accuracy: 53.9 -> 61.7Improved
Use transformation-invariance adaptation instead of entropy minimizationTest-time adaptation on VisDA17 · VisDA17 (batch size 2)accuracy: 12.3 -> 51.2Improved
Use reverse KL rather than forward KL in the invariance objective (ablation)TIPI · Experiments across domains and tasksaccuracyImproved

Later papers that compared with this method

2 later accepted papers report TIPI as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy